Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    terms related to quantitative measurements and their implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Theſe
    -0.72
     Chriftian
    -0.69
     ſeveral
    -0.66
    AnchorStyles
    -0.66
    ſelf
    -0.65
     Jefus
    -0.65
     greateſt
    -0.64
     fhort
    -0.64
     himſelf
    -0.63
     GenerationType
    -0.63
    POSITIVE LOGITS
     its
    0.72
     Its
    0.63
    其
    0.61
    Its
    0.58
    Cyfeiriadau
    0.53
    Enllaces
    0.50
    ніципа
    0.49
     Référence
    0.47
    weiser
    0.46
     prisão
    0.46
    Act Density 0.525%

    No Known Activations